The data is accessible from 2017 to today, we used four entire years of data (2017, 2018, 2019, 2020) to match AIS records.
Code
# Set the path to the 2016 folder#path <- "R/Data/SAR Vessel detections 2017-2020"# List all CSV files in the folder#SAR_csv_files <- list.files(path = here::here(path), pattern = "*.csv", full.names = TRUE)# Read all CSV files and combine them into a single data frame#SAR_fishing <- SAR_csv_files %>%# map_df(~read_csv(.))# Aggregate fishing hours by latitude and longitudeaggregated_SAR_fishing <- SAR_fishing %>%mutate(lat_rounded =round(lat, digits =2),lon_rounded =round(lon, digits =2) ) %>%group_by(lat_rounded, lon_rounded) %>%filter(fishing_score >=0.9) %>%summarise(total_presence_score =sum(presence_score, na.rm =TRUE),avg_fishing_score =mean(fishing_score, na.rm =TRUE),count =n() ) %>%mutate(total_presence_score =round(total_presence_score, digits =0)) %>%ungroup()# Standardize and aggregate SAR dataSAR_data_std <- aggregated_SAR_fishing %>%mutate(coords =map2(lon_rounded, lat_rounded, standardize_coords)) %>%mutate(lon_std =map_dbl(coords, ~ .x$lon_std),lat_std =map_dbl(coords, ~ .x$lat_std) ) %>%group_by(lon_std, lat_std) %>%summarise(total_presence_score =sum(total_presence_score, na.rm =TRUE), .groups ="drop")# Create the world mapworld_map <-map_data("world")# Assign plot to variableSAR_data_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = SAR_data_std, aes(x = lon_std, y = lat_std, fill = total_presence_score)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="Fishing vessel detections (2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title =NULL,x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )print(SAR_data_plot)
Code
# Save the plotggsave(here::here("R","Outputs", "SAR_fishing_map.png"), plot = SAR_data_plot,width =12, height =8, dpi =300)
Compare AIS, and SAR detection locations
Identifying grid cells with only AIS, only SAR detections or both data types.
Code
# Merge the datasetscombined_data <-full_join( AIS_data_std, SAR_data_std,by =c("lon_std", "lat_std"))# Categorize each cellcombined_data <- combined_data %>%mutate(category =case_when( total_fishing_hours >0& total_presence_score >0~"Both AIS and SAR", total_fishing_hours >0& (is.na(total_presence_score) | total_presence_score ==0) ~"Only AIS", (is.na(total_fishing_hours) | total_fishing_hours ==0) & total_presence_score >0~"Only SAR",TRUE~"No fishing detected" ))# Create the world mapworld_map <-map_data("world")# Create the plotworld_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data, aes(x = lon_std, y = lat_std, fill = category)) +scale_fill_manual(values =c("Both AIS and SAR"="purple", "Only AIS"="blue", "Only SAR"="red", "No fishing detected"="white"),name ="Fishing data source",guide =guide_legend(title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global fishing detection",subtitle ="Comparison of AIS (2017-2020) and SAR (2017-2020) data at 0.1-degree resolution",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )# Display the plotprint(world_plot)
Code
# Save the plotggsave(here::here("R","Outputs", "AIS_SAR_comparison_map.png"), plot = world_plot,width =12, height =8, dpi =300)# Get summary statisticssummary_stats <- combined_data %>%count(category) %>%mutate(percentage = n /sum(n) *100) %>%rename(`Number of cells`= n) %>%mutate(percentage =round(percentage, 2))# Create the tabletable_output <-kable(summary_stats, format ="html", col.names =c("Category", "Number of cells", "Percentage (%)"),caption ="Summary statistics of data categories") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =FALSE, position ="center") %>%column_spec(2, width ="150px") %>%column_spec(3, width ="150px")table_output
Summary statistics of data categories
Category
Number of cells
Percentage (%)
Both AIS and SAR
163095
9.12
Only AIS
1566190
87.60
Only SAR
58668
3.28
Code
# Save as PNGsave_kable(table_output, file = here::here("R","Outputs","summary_stats_table.png"))
Random forest model
Predicting fishing hours in areas with only SAR data at a 0.1 degree resolution. Using a random forest model of >160,000 associations between SAR vessel detections and AIS fishing hours globally, geographical coordinates, distance to ports, distance to shore and bathymetry.
Code
# Stack the resampled rastersraster_stack <-stack(Shore_adjusted, Ports_adjusted, Bathy_adjusted)# Convert the stack to a dataframeraster_df <-as.data.frame(raster_stack, xy =TRUE)# Rename the columnsnames(raster_df) <-c("x", "y", "dist_shore", "dist_ports", "bathy")# Remove NA values if desiredraster_df <-na.omit(raster_df)# Convert to data.table for efficiencysetDT(raster_df)# Round x and y to 1 decimal place for consistencyraster_df[, `:=`(lon_std =round(x, digits =1),lat_std =round(y, digits =1))]# Keep only ocean areas (negative bathymetry values)raster_df <- raster_df[bathy <0]# Keep the first occurrence of each coordinate pair (because there are duplicates)raster_df <-unique(raster_df, by =c("lon_std", "lat_std"))setDT(raster_df)# Now proceed with the join and model training#load(here::here("R,"Data","combined_data_O1deg.Rdata"))# Keep the first occurrence of each coordinate pair (because there are duplicates)combined_data_01deg <-unique(combined_data_01deg, by =c("lon_std", "lat_std"))setDT(combined_data_01deg)# Perform the join using data.tablecombined_data_with_rasters <- raster_df[combined_data_01deg, on = .(lon_std, lat_std), nomatch =0]# Convert back to dataframe if neededcombined_data_with_rasters <-as.data.frame(combined_data_with_rasters)# Create the new combined dataframecombined_data_all <- raster_df[, .(lon_std, lat_std, dist_shore, dist_ports, bathy)]# Perform the joincombined_data_all <-merge(combined_data_all, combined_data_01deg, by =c("lon_std", "lat_std"), all.x =TRUE)# Fill NA values for has_AIS and has_SAR with FALSEcombined_data_all[is.na(has_AIS), has_AIS :=FALSE]combined_data_all[is.na(has_SAR), has_SAR :=FALSE]# Categorize each cellcombined_data_all <- combined_data_all %>%mutate(category =case_when( has_AIS ==TRUE~"AIS Data", has_SAR ==TRUE~"SAR Data Only",TRUE~"No AIS or SAR Data" ))# Create the world mapworld_map <-map_data("world")# Create the plotworld_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data_all, aes(x = lon_std, y = lat_std, fill = category, color = category)) +scale_fill_manual(values =c("AIS Data"="blue", "SAR Data Only"="red", "No AIS or SAR Data"="black"),name ="Data Source",guide =guide_legend(title.position ="top", title.hjust =0.5) ) +scale_color_manual(values =c("AIS Data"="blue", "SAR Data Only"="red", "No AIS or SAR Data"="black"),guide ="none" ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global Data Coverage",subtitle ="Distribution of AIS and SAR data at 0.1-degree resolution",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)),panel.grid.major =element_blank(),panel.grid.minor =element_blank(),axis.text =element_text(size =8),axis.title =element_text(size =10),plot.title =element_text(size =14, face ="bold"),plot.subtitle =element_text(size =12) )# Print the plot#print(world_plot)# Calculate summary statisticssummary_stats <- combined_data_all[, .(data_type =case_when( has_AIS ==TRUE~"AIS Data", has_SAR ==TRUE~"SAR Data Only",TRUE~"No AIS or SAR Data" ))][, .(num_cells = .N,percentage = .N /nrow(combined_data_all) *100), by = data_type]# Order the data typessummary_stats <- summary_stats[order(match(data_type, c("AIS Data", "SAR Data Only", "No AIS or SAR Data")))]# Add total rowtotal_row <-data.table(data_type ="Total",num_cells =sum(summary_stats$num_cells),percentage =100)summary_stats <-rbindlist(list(summary_stats, total_row))# Create kablekable_output <- summary_stats %>%kable(col.names =c("Data Type", "Number of Cells", "Percentage (%)"),digits =c(0, 0, 2),align =c("l", "r", "r"),caption ="Summary Statistics of Data Types" ) %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed"), full_width =FALSE) %>%row_spec(nrow(summary_stats), bold =TRUE, background ="#F0F0F0") %>%footnote(general ="AIS Data category includes cells with both AIS and SAR data.",general_title ="Note:",footnote_as_chunk =TRUE )# Print the kable#kable_output# Prepare the training datatraining_data <- combined_data_with_rasters %>%filter(has_AIS & has_SAR) %>% dplyr::select(total_fishing_hours, total_presence_score, lon_std, lat_std, dist_shore, dist_ports, bathy) %>%na.omit()
Comparison of transformations in models
Code
# Prepare the data#load(here::here("R","Data","training_data.Rdata"))#training_data_log <- training_data %>%# mutate(# log_total_presence_score = log10(total_presence_score + 1),# log_total_fishing_hours = log10(total_fishing_hours + 1)# )# Function to run a single model#run_model <- function(formula, data) {# randomForest(# formula,# data = data,# ntree = 500,# importance = TRUE# )#}# Set up parallel processing#num_cores <- detectCores() - 1 # Use all but one core#cl <- makeCluster(num_cores)# Export necessary objects to the cluster#clusterExport(cl, c("training_data_log", "run_model"))# Load required packages on each cluster#clusterEvalQ(cl, library(randomForest))# Define the models#models <- list(# no_transform = as.formula(total_fishing_hours ~ total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy),# original = as.formula(total_fishing_hours ~ log_total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy),# log = as.formula(log_total_fishing_hours ~ log_total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy)#)# Run models in parallel#results <- parLapply(cl, models, function(formula) run_model(formula, training_data_log))# Stop the cluster#stopCluster(cl)# Save the models#rf_model_no_transform <- results[[1]]#rf_model_original <- results[[2]]#rf_model_log <- results[[3]]# Save models to files#saveRDS(rf_model_no_transform, "rf_model_no_transform.rds")#saveRDS(rf_model_original, "rf_model_original.rds")#saveRDS(rf_model_log, "rf_model_log.rds")# Add the new model with only total_fishing_hours log-transformed#rf_model_fishing_log <- randomForest(# log_total_fishing_hours ~ total_presence_score + lon_std + lat_std + dist_shore + dist_ports + bathy,# data = training_data_log,# ntree = 500,# importance = TRUE#)# Save the new model#saveRDS(rf_model_fishing_log, "rf_model_fishing_log.rds")# Function to evaluate modelsevaluate_model <-function(model, data, log_target =FALSE) { predictions <-predict(model, newdata = data)if (log_target) { predictions <-10^predictions -1 } actual <- data$total_fishing_hours# Basic Error Metrics mae <-mean(abs(actual - predictions), na.rm =TRUE) rmse <-sqrt(mean((actual - predictions)^2, na.rm =TRUE)) mape <-mean(abs((actual - predictions) / actual) *100, na.rm =TRUE) medae <-median(abs(actual - predictions), na.rm =TRUE)# R-squared (matching randomForest's % Var explained) r_squared <- model$rsq[length(model$rsq)]# Adjusted R-squared n <-length(actual) p <-length(model$forest$independent.variable.names) # Number of predictors adj_r_squared <-1- ((1- r_squared) * (n -1) / (n - p -1))# Residual Analysis residuals <- actual - predictions mean_residual <-mean(residuals, na.rm =TRUE) sd_residual <-sd(residuals, na.rm =TRUE)# Feature Importance (for Random Forest) feature_importance <-importance(model)return(list("Mean Absolute Error"= mae,"Root Mean Squared Error"= rmse,"Mean Absolute Percentage Error"= mape,"Median Absolute Error"= medae,"R-Squared"= r_squared,"Adjusted R-Squared"= adj_r_squared,"Mean of Residuals"= mean_residual,"Standard Deviation of Residuals"= sd_residual,"Feature Importance"= feature_importance ))}# Evaluate all modelsvalidation_data <- combined_data_with_rasters %>%mutate(data_category =case_when( has_AIS & has_SAR ~"Both AIS and SAR", has_AIS &!has_SAR ~"Only AIS",!has_AIS & has_SAR ~"Only SAR",TRUE~"No fishing detected" ) )validation_data <- validation_data %>%filter(data_category =="Both AIS and SAR")# Evaluate all modelsresults_no_transform <-evaluate_model(rf_model_no_transform, validation_data)validation_data_logpres <- validation_data %>%mutate(log_total_presence_score =log10(total_presence_score +1))results_original <-evaluate_model(rf_model_original, validation_data_logpres)# Add evaluation for the new model (fishing hours log-transformed)results_fishing_log <-evaluate_model(rf_model_fishing_log, validation_data, log_target =TRUE)results_log <-evaluate_model(rf_model_log, validation_data_logpres, log_target =TRUE)# Create a data frame with the resultsresults_df <-data.frame(Metric =c("Mean absolute error", # MAE"Root mean squared error", # RMSE"Mean absolute percentage error", # MAPE"Median absolute error", # MdAE"R-squared", # R² or R2"Adjusted R-squared", # Adj. R²"Mean of residuals","Standard deviation of residuals"),No_Transform =c(results_no_transform$`Mean Absolute Error`, results_no_transform$`Root Mean Squared Error`, results_no_transform$`Mean Absolute Percentage Error`, results_no_transform$`Median Absolute Error`, results_no_transform$`R-Squared`, results_no_transform$`Adjusted R-Squared`, results_no_transform$`Mean of Residuals`, results_no_transform$`Standard Deviation of Residuals`),Fishing_Log =c(results_fishing_log$`Mean Absolute Error`, results_fishing_log$`Root Mean Squared Error`, results_fishing_log$`Mean Absolute Percentage Error`, results_fishing_log$`Median Absolute Error`, results_fishing_log$`R-Squared`, results_fishing_log$`Adjusted R-Squared`, results_fishing_log$`Mean of Residuals`, results_fishing_log$`Standard Deviation of Residuals`),Presence_Log =c(results_original$`Mean Absolute Error`, results_original$`Root Mean Squared Error`, results_original$`Mean Absolute Percentage Error`, results_original$`Median Absolute Error`, results_original$`R-Squared`, results_original$`Adjusted R-Squared`, results_original$`Mean of Residuals`, results_original$`Standard Deviation of Residuals`),Both_Log =c(results_log$`Mean Absolute Error`, results_log$`Root Mean Squared Error`, results_log$`Mean Absolute Percentage Error`, results_log$`Median Absolute Error`, results_log$`R-Squared`, results_log$`Adjusted R-Squared`, results_log$`Mean of Residuals`, results_log$`Standard Deviation of Residuals`))# Create and save the table as HTMLtable_output <-kable(results_df, format ="html", digits =3,col.names =c("Metric", "No transform", "Fishing hours log", "Presence score log", "Both log"),caption ="Model performance comparison") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =FALSE) %>%add_header_above(c(" "=1, "Models"=4)) %>%column_spec(1, bold =TRUE)# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "model_performance.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "model_performance.html"), here::here("R", "Outputs", "model_performance.png"),vwidth =800, # Width in pixelsvheight =400, # Height in pixels - adjust as neededzoom =2)
Interpretation of model comparison metrics
Based on the provided performance metrics, I would choose the Fishing Hours Log-Transformed Model. Here’s the reasoning:
R-Squared and Adjusted R-Squared: The Fishing Hours Log model has the highest R-squared (0.8239) and Adjusted R-squared values, indicating it explains the most variance in the data.
Mean Absolute Percentage Error (MAPE): This model has a significantly lower MAPE (69.71%) compared to the No Transform and Presence Log models (both over 1200%). This suggests much better relative accuracy. Median Absolute Error: It has the lowest median absolute error (10.19), which indicates good performance on typical cases.
Root Mean Squared Error (RMSE): While higher than the No Transform model, the difference isn’t as dramatic as the improvement in MAPE.
Mean Absolute Error (MAE): Although higher than No Transform and Presence Log models, this should be considered in context with other metrics.
The Both Log model performs very similarly to the Fishing Hours Log model, but the latter edges it out slightly in most metrics.
The No Transform and Presence Log models, despite having lower MAE and RMSE, have extremely high MAPE values, suggesting they might be making large relative errors, especially on smaller values.
The logarithmic transformation of fishing hours seems to have addressed some issues with the data distribution, leading to more balanced performance across different scales of the target variable.
In conclusion, the Fishing Hours Log-Transformed Model appears to offer the best overall performance, particularly in terms of explained variance and relative error metrics. However, the choice might depend on the specific requirements of your application, such as whether absolute or relative errors are more important in your context.
Selected Model performance
Code
evaluate_model <-function(model, data, log_target =FALSE) { predictions <-predict(model, newdata = data)if (log_target) { predictions <-10^predictions -1 } actual <-if (log_target) 10^data$log_total_fishing_hours -1else data$total_fishing_hours# Basic Error Metrics mae <-mean(abs(actual - predictions), na.rm =TRUE) rmse <-sqrt(mean((actual - predictions)^2, na.rm =TRUE)) mape <-mean(abs((actual - predictions) / actual) *100, na.rm =TRUE) medae <-median(abs(actual - predictions), na.rm =TRUE)# R-squared (matching randomForest's % Var explained) r_squared <- model$rsq[length(model$rsq)]# Adjusted R-squared n <-length(actual) p <-length(model$forest$independent.variable.names) adj_r_squared <-1- ((1- r_squared) * (n -1) / (n - p -1))# Residual Analysis residuals <- actual - predictions mean_residual <-mean(residuals, na.rm =TRUE) sd_residual <-sd(residuals, na.rm =TRUE)# Feature Importance (for Random Forest) feature_importance <-importance(model)return(list("Mean absolute error"= mae,"Root mean squared error"= rmse,"Mean absolute percentage error"= mape,"Median absolute error"= medae, # FIXED TYPO"R-squared"= r_squared,"Adjusted R-squared"= adj_r_squared, # FIXED CASE"Mean of residuals"= mean_residual,"Standard deviation of residuals"= sd_residual,"Feature importance"= feature_importance ))}validation_data <- combined_data_with_rasters %>%mutate(data_category =case_when( has_AIS & has_SAR ~"Both AIS and SAR", has_AIS &!has_SAR ~"Only AIS",!has_AIS & has_SAR ~"Only SAR",TRUE~"No fishing detected" ),log_total_fishing_hours =log10(total_fishing_hours +1) )# Evaluate the modelvalidation_data <- validation_data %>%filter(data_category =="Both AIS and SAR")results_rf_fishing_log <-evaluate_model(rf_model_fishing_log, validation_data, log_target =TRUE)# Create a dataframe for the tableresults_table <-data.frame(Metric =c("Mean absolute error", "Root mean squared error", "Mean absolute percentage error","Median absolute error", "R-squared", "Adjusted R-squared","Mean of residuals", "Standard deviation of residuals"),Value =round(c(results_rf_fishing_log$`Mean absolute error`, results_rf_fishing_log$`Root mean squared error`, results_rf_fishing_log$`Mean absolute percentage error`, results_rf_fishing_log$`Median absolute error`, # FIXED: was "Median ebsolute error" results_rf_fishing_log$`R-squared`, results_rf_fishing_log$`Adjusted R-squared`, # FIXED: was "Adjusted r-squared" results_rf_fishing_log$`Mean of residuals`, results_rf_fishing_log$`Standard deviation of residuals`),2))table_output <-kable(results_table, format ="html", digits =4, caption ="Model evaluation metrics for log-transformed fishing hours model") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =TRUE,position ="center")# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "model_evaluation.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "model_evaluation.html"), here::here("R", "Outputs", "model_evaluation.png"),vwidth =800, # Width in pixelsvheight =360, # Height in pixels - adjust as neededzoom =2)
Code
# For feature importance, create a separate table# Use $ before the backticksfeature_importance <-as.data.frame(results_rf_fishing_log$`Feature importance`)feature_importance$Feature <-rownames(feature_importance)feature_importance <- feature_importance[, c("Feature", "%IncMSE", "IncNodePurity")]colnames(feature_importance) <-c("Feature", "%IncMSE", "IncNodePurity")# Sort the feature importance table by %IncMSE in descending orderfeature_importance <- feature_importance[order(-feature_importance$`%IncMSE`), ]# Create the tabletable_output <-kable(feature_importance, format ="html", digits =4, col.names =c("Feature", "%IncMSE", "IncNodePurity"),caption ="Feature importance for log-transformed fishing hours model") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =TRUE, position ="center") %>%column_spec(1, bold =TRUE) %>%column_spec(2:3, width ="150px")# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "feature_importance.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "feature_importance.html"), here::here("R", "Outputs", "feature_importance.png"),vwidth =720, # Width in pixelsvheight =300, # Height in pixels - adjust as neededzoom =2)
Maps of predictions
Code
# Prepare the prediction dataprediction_data <- combined_data_with_rasters %>% dplyr::select(total_presence_score, lon_std, lat_std, dist_shore, dist_ports, bathy)# Make predictionslog_predictions <-predict(rf_model_fishing_log, newdata = prediction_data)# Back-transform predictionspredictions <-10^log_predictions -1# Add predictions to the original datasetcombined_data_01deg <- combined_data_01deg %>%mutate(predicted_fishing_hours =case_when( has_AIS ~ total_fishing_hours, has_SAR ~ predictions[match(paste(lon_std, lat_std), paste(prediction_data$lon_std, prediction_data$lat_std))],TRUE~0 ) )#Violin plot of observed versus predicted fishing hours # Prepare data for plottingplot_data <- combined_data_01deg %>%mutate(ais_fishing_hours =if_else(has_AIS, total_fishing_hours, NA_real_),sar_predicted_hours =if_else(!has_AIS & has_SAR, predicted_fishing_hours, NA_real_) ) %>% dplyr::select(ais_fishing_hours, sar_predicted_hours) %>%pivot_longer(cols =c(ais_fishing_hours, sar_predicted_hours),names_to ="type",values_to ="hours") %>%filter(!is.na(hours))# Create violin plotviolin_plot <-ggplot(plot_data, aes(x = type, y = hours, fill = type)) +geom_violin(trim =FALSE) +geom_boxplot(width =0.1, fill ="white", color ="black", alpha =0.5, outlier.shape =NA) +scale_y_log10(labels = scales::comma_format(accuracy =1)) +scale_x_discrete(labels =c("ais_fishing_hours"="AIS Data", "sar_predicted_hours"="SAR Predictions")) +labs(title ="Comparison of AIS Fishing Hours and SAR Predicted Fishing Hours",subtitle ="AIS data for AIS-covered areas, Predictions for SAR-only areas",x ="",y ="Fishing Hours (log scale)",fill ="Type") +theme_minimal() +theme(legend.position ="none",axis.text.x =element_text(angle =45, hjust =1))# Print the plotprint(violin_plot)
Code
# Map of predicted fishing hours only # Prepare the data for the mapmap_data <- combined_data_01deg %>%filter(!has_AIS & has_SAR) %>% dplyr::select(lon_std, lat_std, predicted_fishing_hours)# The map_data now contains back-transformed predictions, so no further transformation is needed#predicted_SAR_only_1RF=map_data#save(predicted_SAR_only_1RF, file="predicted_SAR_only_1RF.Rdata")# Create the world mapworld_map <-map_data("world")# Function to create map for a specific regioncreate_region_map <-function(data, world_map, lon_col, lat_col, lon_range, lat_range, title, subtitle) {ggplot() +geom_map(data = world_map, map = world_map,aes(long, lat, map_id = region),color ="darkgray", fill ="lightgray", size =0.1) +geom_tile(data = data, aes(x = .data[[lon_col]], y = .data[[lat_col]], fill = predicted_fishing_hours)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="Predicted fishing hours (2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000, 100000, 1000000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3, xlim = lon_range, ylim = lat_range) +theme_minimal() +labs(title = title,subtitle = subtitle,x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )}# Global mappredicted_SAR_only_plot <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-180, 180), c(-90, 90), "Predicted Fishing Hours in Areas with Only SAR Detections", "0.1 degree resolution")# Caribbean mapcaribbean_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-100, -50), c(0, 40), "Predicted Fishing Hours in the Caribbean", "0.1 degree resolution")# Northwestern Indian Ocean to Western European waters mapindian_european_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-20, 80), c(0, 70), "Predicted Fishing Hours from Northern Indian Ocean \nto Eastern Atlantic", "0.1 degree resolution")# Asia mapasia_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(60, 180), c(-20, 60), "Predicted Fishing Hours in Asia", "0.1 degree resolution")# Print the maps#print(predicted_SAR_only_plot)print(caribbean_map)
Code
print(indian_european_map)
Code
print(asia_map)
Code
#Map of both original and predicted AIS fishing hours # Visualize the resultspredicted_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long, lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data_01deg, aes(x = lon_std, y = lat_std, fill = predicted_fishing_hours)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="AIS fishing effort (hours; 2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000, 100000, 1000000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global fishing hours (0.1 degree resolution)",subtitle ="Based on AIS data and random forest predictions from SAR data",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )print(predicted_plot)
Code
# Save the plotggsave(here::here("R", "Outputs", "predicted_plot_SAR_only.png"), plot = predicted_plot,width =12, height =8, dpi =300)
Source Code
---title: "Manuscript_fishing_hours"author: "Théophile L. Mouton"date: "`r Sys.Date()`"format: html: toc: true toc-location: right css: custom.css output-file: "Manuscript_fishing_hours.html" self-contained: true code-fold: true code-tools: trueeditor: visualexecute: warning: false error: falseparams: printlabels: TRUE---## Open R libraries```{r}library(tidyverse)library(tidyr)library(ggplot2)library(data.table)library(gridExtra)library(maps)library(raster)library(sf)library(viridis)library(scales)library(dplyr)library(randomForest)library(caret)library(pdp)library(knitr)library(kableExtra)library(future)library(spdep)library(ncf)library(blockCV)library(parallel)library(doParallel)library(sp)library(purrr)library(kableExtra)library(webshot2)```## Open datasets```{r}#AIS dataload(here::here("R","Data","AIS_fishing.Rdata"))#SAR dataload(here::here("R","Data","SAR_fishing.Rdata"))# Open the saved adjusted rastersPorts_adjusted <-raster(here::here("R", "Data", "distance-from-port-0.1deg-adjusted.tif"))Shore_adjusted <-raster(here::here("R", "Data", "distance-from-shore-0.1deg-adjusted.tif"))Bathy_adjusted <-raster(here::here("R", "Data", "bathymetry-0.1deg-adjusted.tif"))#load(here::here("R", "Data","combined_data_O1deg.Rdata"))# Load the saved RF modelsrf_model_no_transform <-readRDS(here::here("R", "Data", "rf_model_no_transform.rds"))rf_model_original <-readRDS(here::here("R", "Data", "rf_model_original.rds"))rf_model_log <-readRDS(here::here("R", "Data", "rf_model_log.rds"))rf_model_fishing_log <-readRDS(here::here("R", "Data", "rf_model_fishing_log.rds"))```## AIS dataData from Kroodsma et al. (2018) Science, accessible at: [Global Fishing Watch Data Download Portal](https://globalfishingwatch.org/data-download/datasets/public-fishing-effort).The data is accessible up to the end of the year 2020, we used four entire years of data (2017, 2018, 2019, 2020) to match SAR data records.```{r}# Set the path to the 2017-2020 folder#path <- "R/Data/AIS Fishing Effort 2017-2020"# List all CSV files in the folder#AIS_csv_files <- list.files(path = here::here(path), pattern = "*.csv", full.names = TRUE, recursive = TRUE)# Read all CSV files and combine them into a single data frame#AIS_fishing <- AIS_csv_files %>%# map_df(~read_csv(.))# Aggregate fishing hours by latitude and longitudeaggregated_AIS_fishing <- AIS_fishing %>%group_by(cell_ll_lat, cell_ll_lon) %>%summarise(total_fishing_hours =sum(fishing_hours, na.rm =TRUE)) %>%ungroup() %>%# Remove any cells with zero or negative fishing hoursfilter(total_fishing_hours >0)# Function to standardize coordinates to 0.1 degree resolutionstandardize_coords <-function(lon, lat) {list(lon_std =floor(lon *10) /10,lat_std =floor(lat *10) /10 )}# Standardize and aggregate AIS dataAIS_data_std <- aggregated_AIS_fishing %>%mutate(coords =map2(cell_ll_lon, cell_ll_lat, standardize_coords)) %>%mutate(lon_std =map_dbl(coords, ~ .x$lon_std),lat_std =map_dbl(coords, ~ .x$lat_std) ) %>%group_by(lon_std, lat_std) %>%summarise(total_fishing_hours =sum(total_fishing_hours, na.rm =TRUE), .groups ="drop")# Create the world mapworld_map <-map_data("world")# Assign plot to variableAIS_data_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = AIS_data_std, aes(x = lon_std, y = lat_std, fill = total_fishing_hours)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="AIS fishing effort (hours; 2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000, 100000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title =NULL,x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )print(AIS_data_plot)# Save the plotggsave(here::here("R","Outputs","AIS_fishing_map.png"), plot = AIS_data_plot,width =12, height =8, dpi =300)```## Sentinel-1 SAR dataData from Paolo et al. 2024 Nature, accessible at: [Global Fishing Watch SAR Vessel Detections](https://globalfishingwatch.org/data-download/datasets/public-sar-vessel-detections:v20231026)The data is accessible from 2017 to today, we used four entire years of data (2017, 2018, 2019, 2020) to match AIS records.```{r}# Set the path to the 2016 folder#path <- "R/Data/SAR Vessel detections 2017-2020"# List all CSV files in the folder#SAR_csv_files <- list.files(path = here::here(path), pattern = "*.csv", full.names = TRUE)# Read all CSV files and combine them into a single data frame#SAR_fishing <- SAR_csv_files %>%# map_df(~read_csv(.))# Aggregate fishing hours by latitude and longitudeaggregated_SAR_fishing <- SAR_fishing %>%mutate(lat_rounded =round(lat, digits =2),lon_rounded =round(lon, digits =2) ) %>%group_by(lat_rounded, lon_rounded) %>%filter(fishing_score >=0.9) %>%summarise(total_presence_score =sum(presence_score, na.rm =TRUE),avg_fishing_score =mean(fishing_score, na.rm =TRUE),count =n() ) %>%mutate(total_presence_score =round(total_presence_score, digits =0)) %>%ungroup()# Standardize and aggregate SAR dataSAR_data_std <- aggregated_SAR_fishing %>%mutate(coords =map2(lon_rounded, lat_rounded, standardize_coords)) %>%mutate(lon_std =map_dbl(coords, ~ .x$lon_std),lat_std =map_dbl(coords, ~ .x$lat_std) ) %>%group_by(lon_std, lat_std) %>%summarise(total_presence_score =sum(total_presence_score, na.rm =TRUE), .groups ="drop")# Create the world mapworld_map <-map_data("world")# Assign plot to variableSAR_data_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = SAR_data_std, aes(x = lon_std, y = lat_std, fill = total_presence_score)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="Fishing vessel detections (2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title =NULL,x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )print(SAR_data_plot)# Save the plotggsave(here::here("R","Outputs", "SAR_fishing_map.png"), plot = SAR_data_plot,width =12, height =8, dpi =300)```## Compare AIS, and SAR detection locationsIdentifying grid cells with only AIS, only SAR detections or both data types.```{r}# Merge the datasetscombined_data <-full_join( AIS_data_std, SAR_data_std,by =c("lon_std", "lat_std"))# Categorize each cellcombined_data <- combined_data %>%mutate(category =case_when( total_fishing_hours >0& total_presence_score >0~"Both AIS and SAR", total_fishing_hours >0& (is.na(total_presence_score) | total_presence_score ==0) ~"Only AIS", (is.na(total_fishing_hours) | total_fishing_hours ==0) & total_presence_score >0~"Only SAR",TRUE~"No fishing detected" ))# Create the world mapworld_map <-map_data("world")# Create the plotworld_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data, aes(x = lon_std, y = lat_std, fill = category)) +scale_fill_manual(values =c("Both AIS and SAR"="purple", "Only AIS"="blue", "Only SAR"="red", "No fishing detected"="white"),name ="Fishing data source",guide =guide_legend(title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global fishing detection",subtitle ="Comparison of AIS (2017-2020) and SAR (2017-2020) data at 0.1-degree resolution",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )# Display the plotprint(world_plot)# Save the plotggsave(here::here("R","Outputs", "AIS_SAR_comparison_map.png"), plot = world_plot,width =12, height =8, dpi =300)# Get summary statisticssummary_stats <- combined_data %>%count(category) %>%mutate(percentage = n /sum(n) *100) %>%rename(`Number of cells`= n) %>%mutate(percentage =round(percentage, 2))# Create the tabletable_output <-kable(summary_stats, format ="html", col.names =c("Category", "Number of cells", "Percentage (%)"),caption ="Summary statistics of data categories") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =FALSE, position ="center") %>%column_spec(2, width ="150px") %>%column_spec(3, width ="150px")table_output# Save as PNGsave_kable(table_output, file = here::here("R","Outputs","summary_stats_table.png"))```## Random forest modelPredicting fishing hours in areas with only SAR data at a 0.1 degree resolution. Using a random forest model of \>160,000 associations between SAR vessel detections and AIS fishing hours globally, geographical coordinates, distance to ports, distance to shore and bathymetry.```{r}# Stack the resampled rastersraster_stack <-stack(Shore_adjusted, Ports_adjusted, Bathy_adjusted)# Convert the stack to a dataframeraster_df <-as.data.frame(raster_stack, xy =TRUE)# Rename the columnsnames(raster_df) <-c("x", "y", "dist_shore", "dist_ports", "bathy")# Remove NA values if desiredraster_df <-na.omit(raster_df)# Convert to data.table for efficiencysetDT(raster_df)# Round x and y to 1 decimal place for consistencyraster_df[, `:=`(lon_std =round(x, digits =1),lat_std =round(y, digits =1))]# Keep only ocean areas (negative bathymetry values)raster_df <- raster_df[bathy <0]# Keep the first occurrence of each coordinate pair (because there are duplicates)raster_df <-unique(raster_df, by =c("lon_std", "lat_std"))setDT(raster_df)# Now proceed with the join and model training#load(here::here("R,"Data","combined_data_O1deg.Rdata"))# Keep the first occurrence of each coordinate pair (because there are duplicates)combined_data_01deg <-unique(combined_data_01deg, by =c("lon_std", "lat_std"))setDT(combined_data_01deg)# Perform the join using data.tablecombined_data_with_rasters <- raster_df[combined_data_01deg, on = .(lon_std, lat_std), nomatch =0]# Convert back to dataframe if neededcombined_data_with_rasters <-as.data.frame(combined_data_with_rasters)# Create the new combined dataframecombined_data_all <- raster_df[, .(lon_std, lat_std, dist_shore, dist_ports, bathy)]# Perform the joincombined_data_all <-merge(combined_data_all, combined_data_01deg, by =c("lon_std", "lat_std"), all.x =TRUE)# Fill NA values for has_AIS and has_SAR with FALSEcombined_data_all[is.na(has_AIS), has_AIS :=FALSE]combined_data_all[is.na(has_SAR), has_SAR :=FALSE]# Categorize each cellcombined_data_all <- combined_data_all %>%mutate(category =case_when( has_AIS ==TRUE~"AIS Data", has_SAR ==TRUE~"SAR Data Only",TRUE~"No AIS or SAR Data" ))# Create the world mapworld_map <-map_data("world")# Create the plotworld_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long = long, lat = lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data_all, aes(x = lon_std, y = lat_std, fill = category, color = category)) +scale_fill_manual(values =c("AIS Data"="blue", "SAR Data Only"="red", "No AIS or SAR Data"="black"),name ="Data Source",guide =guide_legend(title.position ="top", title.hjust =0.5) ) +scale_color_manual(values =c("AIS Data"="blue", "SAR Data Only"="red", "No AIS or SAR Data"="black"),guide ="none" ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global Data Coverage",subtitle ="Distribution of AIS and SAR data at 0.1-degree resolution",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)),panel.grid.major =element_blank(),panel.grid.minor =element_blank(),axis.text =element_text(size =8),axis.title =element_text(size =10),plot.title =element_text(size =14, face ="bold"),plot.subtitle =element_text(size =12) )# Print the plot#print(world_plot)# Calculate summary statisticssummary_stats <- combined_data_all[, .(data_type =case_when( has_AIS ==TRUE~"AIS Data", has_SAR ==TRUE~"SAR Data Only",TRUE~"No AIS or SAR Data" ))][, .(num_cells = .N,percentage = .N /nrow(combined_data_all) *100), by = data_type]# Order the data typessummary_stats <- summary_stats[order(match(data_type, c("AIS Data", "SAR Data Only", "No AIS or SAR Data")))]# Add total rowtotal_row <-data.table(data_type ="Total",num_cells =sum(summary_stats$num_cells),percentage =100)summary_stats <-rbindlist(list(summary_stats, total_row))# Create kablekable_output <- summary_stats %>%kable(col.names =c("Data Type", "Number of Cells", "Percentage (%)"),digits =c(0, 0, 2),align =c("l", "r", "r"),caption ="Summary Statistics of Data Types" ) %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed"), full_width =FALSE) %>%row_spec(nrow(summary_stats), bold =TRUE, background ="#F0F0F0") %>%footnote(general ="AIS Data category includes cells with both AIS and SAR data.",general_title ="Note:",footnote_as_chunk =TRUE )# Print the kable#kable_output# Prepare the training datatraining_data <- combined_data_with_rasters %>%filter(has_AIS & has_SAR) %>% dplyr::select(total_fishing_hours, total_presence_score, lon_std, lat_std, dist_shore, dist_ports, bathy) %>%na.omit()```### Comparison of transformations in models```{r}# Prepare the data#load(here::here("R","Data","training_data.Rdata"))#training_data_log <- training_data %>%# mutate(# log_total_presence_score = log10(total_presence_score + 1),# log_total_fishing_hours = log10(total_fishing_hours + 1)# )# Function to run a single model#run_model <- function(formula, data) {# randomForest(# formula,# data = data,# ntree = 500,# importance = TRUE# )#}# Set up parallel processing#num_cores <- detectCores() - 1 # Use all but one core#cl <- makeCluster(num_cores)# Export necessary objects to the cluster#clusterExport(cl, c("training_data_log", "run_model"))# Load required packages on each cluster#clusterEvalQ(cl, library(randomForest))# Define the models#models <- list(# no_transform = as.formula(total_fishing_hours ~ total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy),# original = as.formula(total_fishing_hours ~ log_total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy),# log = as.formula(log_total_fishing_hours ~ log_total_presence_score + lon_std + lat_std + dist_shore + #dist_ports + bathy)#)# Run models in parallel#results <- parLapply(cl, models, function(formula) run_model(formula, training_data_log))# Stop the cluster#stopCluster(cl)# Save the models#rf_model_no_transform <- results[[1]]#rf_model_original <- results[[2]]#rf_model_log <- results[[3]]# Save models to files#saveRDS(rf_model_no_transform, "rf_model_no_transform.rds")#saveRDS(rf_model_original, "rf_model_original.rds")#saveRDS(rf_model_log, "rf_model_log.rds")# Add the new model with only total_fishing_hours log-transformed#rf_model_fishing_log <- randomForest(# log_total_fishing_hours ~ total_presence_score + lon_std + lat_std + dist_shore + dist_ports + bathy,# data = training_data_log,# ntree = 500,# importance = TRUE#)# Save the new model#saveRDS(rf_model_fishing_log, "rf_model_fishing_log.rds")# Function to evaluate modelsevaluate_model <-function(model, data, log_target =FALSE) { predictions <-predict(model, newdata = data)if (log_target) { predictions <-10^predictions -1 } actual <- data$total_fishing_hours# Basic Error Metrics mae <-mean(abs(actual - predictions), na.rm =TRUE) rmse <-sqrt(mean((actual - predictions)^2, na.rm =TRUE)) mape <-mean(abs((actual - predictions) / actual) *100, na.rm =TRUE) medae <-median(abs(actual - predictions), na.rm =TRUE)# R-squared (matching randomForest's % Var explained) r_squared <- model$rsq[length(model$rsq)]# Adjusted R-squared n <-length(actual) p <-length(model$forest$independent.variable.names) # Number of predictors adj_r_squared <-1- ((1- r_squared) * (n -1) / (n - p -1))# Residual Analysis residuals <- actual - predictions mean_residual <-mean(residuals, na.rm =TRUE) sd_residual <-sd(residuals, na.rm =TRUE)# Feature Importance (for Random Forest) feature_importance <-importance(model)return(list("Mean Absolute Error"= mae,"Root Mean Squared Error"= rmse,"Mean Absolute Percentage Error"= mape,"Median Absolute Error"= medae,"R-Squared"= r_squared,"Adjusted R-Squared"= adj_r_squared,"Mean of Residuals"= mean_residual,"Standard Deviation of Residuals"= sd_residual,"Feature Importance"= feature_importance ))}# Evaluate all modelsvalidation_data <- combined_data_with_rasters %>%mutate(data_category =case_when( has_AIS & has_SAR ~"Both AIS and SAR", has_AIS &!has_SAR ~"Only AIS",!has_AIS & has_SAR ~"Only SAR",TRUE~"No fishing detected" ) )validation_data <- validation_data %>%filter(data_category =="Both AIS and SAR")# Evaluate all modelsresults_no_transform <-evaluate_model(rf_model_no_transform, validation_data)validation_data_logpres <- validation_data %>%mutate(log_total_presence_score =log10(total_presence_score +1))results_original <-evaluate_model(rf_model_original, validation_data_logpres)# Add evaluation for the new model (fishing hours log-transformed)results_fishing_log <-evaluate_model(rf_model_fishing_log, validation_data, log_target =TRUE)results_log <-evaluate_model(rf_model_log, validation_data_logpres, log_target =TRUE)# Create a data frame with the resultsresults_df <-data.frame(Metric =c("Mean absolute error", # MAE"Root mean squared error", # RMSE"Mean absolute percentage error", # MAPE"Median absolute error", # MdAE"R-squared", # R² or R2"Adjusted R-squared", # Adj. R²"Mean of residuals","Standard deviation of residuals"),No_Transform =c(results_no_transform$`Mean Absolute Error`, results_no_transform$`Root Mean Squared Error`, results_no_transform$`Mean Absolute Percentage Error`, results_no_transform$`Median Absolute Error`, results_no_transform$`R-Squared`, results_no_transform$`Adjusted R-Squared`, results_no_transform$`Mean of Residuals`, results_no_transform$`Standard Deviation of Residuals`),Fishing_Log =c(results_fishing_log$`Mean Absolute Error`, results_fishing_log$`Root Mean Squared Error`, results_fishing_log$`Mean Absolute Percentage Error`, results_fishing_log$`Median Absolute Error`, results_fishing_log$`R-Squared`, results_fishing_log$`Adjusted R-Squared`, results_fishing_log$`Mean of Residuals`, results_fishing_log$`Standard Deviation of Residuals`),Presence_Log =c(results_original$`Mean Absolute Error`, results_original$`Root Mean Squared Error`, results_original$`Mean Absolute Percentage Error`, results_original$`Median Absolute Error`, results_original$`R-Squared`, results_original$`Adjusted R-Squared`, results_original$`Mean of Residuals`, results_original$`Standard Deviation of Residuals`),Both_Log =c(results_log$`Mean Absolute Error`, results_log$`Root Mean Squared Error`, results_log$`Mean Absolute Percentage Error`, results_log$`Median Absolute Error`, results_log$`R-Squared`, results_log$`Adjusted R-Squared`, results_log$`Mean of Residuals`, results_log$`Standard Deviation of Residuals`))# Create and save the table as HTMLtable_output <-kable(results_df, format ="html", digits =3,col.names =c("Metric", "No transform", "Fishing hours log", "Presence score log", "Both log"),caption ="Model performance comparison") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =FALSE) %>%add_header_above(c(" "=1, "Models"=4)) %>%column_spec(1, bold =TRUE)# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "model_performance.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "model_performance.html"), here::here("R", "Outputs", "model_performance.png"),vwidth =800, # Width in pixelsvheight =400, # Height in pixels - adjust as neededzoom =2)```#### Interpretation of model comparison metricsBased on the provided performance metrics, I would choose the Fishing Hours Log-Transformed Model. Here's the reasoning:1. R-Squared and Adjusted R-Squared: The Fishing Hours Log model has the highest R-squared (0.8239) and Adjusted R-squared values, indicating it explains the most variance in the data.2. Mean Absolute Percentage Error (MAPE): This model has a significantly lower MAPE (69.71%) compared to the No Transform and Presence Log models (both over 1200%). This suggests much better relative accuracy. Median Absolute Error: It has the lowest median absolute error (10.19), which indicates good performance on typical cases.3. Root Mean Squared Error (RMSE): While higher than the No Transform model, the difference isn't as dramatic as the improvement in MAPE.4. Mean Absolute Error (MAE): Although higher than No Transform and Presence Log models, this should be considered in context with other metrics.The Both Log model performs very similarly to the Fishing Hours Log model, but the latter edges it out slightly in most metrics.The No Transform and Presence Log models, despite having lower MAE and RMSE, have extremely high MAPE values, suggesting they might be making large relative errors, especially on smaller values.The logarithmic transformation of fishing hours seems to have addressed some issues with the data distribution, leading to more balanced performance across different scales of the target variable.In conclusion, the Fishing Hours Log-Transformed Model appears to offer the best overall performance, particularly in terms of explained variance and relative error metrics. However, the choice might depend on the specific requirements of your application, such as whether absolute or relative errors are more important in your context.### Selected Model performance```{r}evaluate_model <-function(model, data, log_target =FALSE) { predictions <-predict(model, newdata = data)if (log_target) { predictions <-10^predictions -1 } actual <-if (log_target) 10^data$log_total_fishing_hours -1else data$total_fishing_hours# Basic Error Metrics mae <-mean(abs(actual - predictions), na.rm =TRUE) rmse <-sqrt(mean((actual - predictions)^2, na.rm =TRUE)) mape <-mean(abs((actual - predictions) / actual) *100, na.rm =TRUE) medae <-median(abs(actual - predictions), na.rm =TRUE)# R-squared (matching randomForest's % Var explained) r_squared <- model$rsq[length(model$rsq)]# Adjusted R-squared n <-length(actual) p <-length(model$forest$independent.variable.names) adj_r_squared <-1- ((1- r_squared) * (n -1) / (n - p -1))# Residual Analysis residuals <- actual - predictions mean_residual <-mean(residuals, na.rm =TRUE) sd_residual <-sd(residuals, na.rm =TRUE)# Feature Importance (for Random Forest) feature_importance <-importance(model)return(list("Mean absolute error"= mae,"Root mean squared error"= rmse,"Mean absolute percentage error"= mape,"Median absolute error"= medae, # FIXED TYPO"R-squared"= r_squared,"Adjusted R-squared"= adj_r_squared, # FIXED CASE"Mean of residuals"= mean_residual,"Standard deviation of residuals"= sd_residual,"Feature importance"= feature_importance ))}validation_data <- combined_data_with_rasters %>%mutate(data_category =case_when( has_AIS & has_SAR ~"Both AIS and SAR", has_AIS &!has_SAR ~"Only AIS",!has_AIS & has_SAR ~"Only SAR",TRUE~"No fishing detected" ),log_total_fishing_hours =log10(total_fishing_hours +1) )# Evaluate the modelvalidation_data <- validation_data %>%filter(data_category =="Both AIS and SAR")results_rf_fishing_log <-evaluate_model(rf_model_fishing_log, validation_data, log_target =TRUE)# Create a dataframe for the tableresults_table <-data.frame(Metric =c("Mean absolute error", "Root mean squared error", "Mean absolute percentage error","Median absolute error", "R-squared", "Adjusted R-squared","Mean of residuals", "Standard deviation of residuals"),Value =round(c(results_rf_fishing_log$`Mean absolute error`, results_rf_fishing_log$`Root mean squared error`, results_rf_fishing_log$`Mean absolute percentage error`, results_rf_fishing_log$`Median absolute error`, # FIXED: was "Median ebsolute error" results_rf_fishing_log$`R-squared`, results_rf_fishing_log$`Adjusted R-squared`, # FIXED: was "Adjusted r-squared" results_rf_fishing_log$`Mean of residuals`, results_rf_fishing_log$`Standard deviation of residuals`),2))table_output <-kable(results_table, format ="html", digits =4, caption ="Model evaluation metrics for log-transformed fishing hours model") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =TRUE,position ="center")# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "model_evaluation.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "model_evaluation.html"), here::here("R", "Outputs", "model_evaluation.png"),vwidth =800, # Width in pixelsvheight =360, # Height in pixels - adjust as neededzoom =2)# For feature importance, create a separate table# Use $ before the backticksfeature_importance <-as.data.frame(results_rf_fishing_log$`Feature importance`)feature_importance$Feature <-rownames(feature_importance)feature_importance <- feature_importance[, c("Feature", "%IncMSE", "IncNodePurity")]colnames(feature_importance) <-c("Feature", "%IncMSE", "IncNodePurity")# Sort the feature importance table by %IncMSE in descending orderfeature_importance <- feature_importance[order(-feature_importance$`%IncMSE`), ]# Create the tabletable_output <-kable(feature_importance, format ="html", digits =4, col.names =c("Feature", "%IncMSE", "IncNodePurity"),caption ="Feature importance for log-transformed fishing hours model") %>%kable_styling(bootstrap_options =c("striped", "hover", "condensed", "responsive"),full_width =TRUE, position ="center") %>%column_spec(1, bold =TRUE) %>%column_spec(2:3, width ="150px")# Save as HTML firstsave_kable(table_output, file = here::here("R", "Outputs", "feature_importance.html"))# Then screenshot with custom viewportwebshot(here::here("R", "Outputs", "feature_importance.html"), here::here("R", "Outputs", "feature_importance.png"),vwidth =720, # Width in pixelsvheight =300, # Height in pixels - adjust as neededzoom =2)```### Maps of predictions```{r}# Prepare the prediction dataprediction_data <- combined_data_with_rasters %>% dplyr::select(total_presence_score, lon_std, lat_std, dist_shore, dist_ports, bathy)# Make predictionslog_predictions <-predict(rf_model_fishing_log, newdata = prediction_data)# Back-transform predictionspredictions <-10^log_predictions -1# Add predictions to the original datasetcombined_data_01deg <- combined_data_01deg %>%mutate(predicted_fishing_hours =case_when( has_AIS ~ total_fishing_hours, has_SAR ~ predictions[match(paste(lon_std, lat_std), paste(prediction_data$lon_std, prediction_data$lat_std))],TRUE~0 ) )#Violin plot of observed versus predicted fishing hours # Prepare data for plottingplot_data <- combined_data_01deg %>%mutate(ais_fishing_hours =if_else(has_AIS, total_fishing_hours, NA_real_),sar_predicted_hours =if_else(!has_AIS & has_SAR, predicted_fishing_hours, NA_real_) ) %>% dplyr::select(ais_fishing_hours, sar_predicted_hours) %>%pivot_longer(cols =c(ais_fishing_hours, sar_predicted_hours),names_to ="type",values_to ="hours") %>%filter(!is.na(hours))# Create violin plotviolin_plot <-ggplot(plot_data, aes(x = type, y = hours, fill = type)) +geom_violin(trim =FALSE) +geom_boxplot(width =0.1, fill ="white", color ="black", alpha =0.5, outlier.shape =NA) +scale_y_log10(labels = scales::comma_format(accuracy =1)) +scale_x_discrete(labels =c("ais_fishing_hours"="AIS Data", "sar_predicted_hours"="SAR Predictions")) +labs(title ="Comparison of AIS Fishing Hours and SAR Predicted Fishing Hours",subtitle ="AIS data for AIS-covered areas, Predictions for SAR-only areas",x ="",y ="Fishing Hours (log scale)",fill ="Type") +theme_minimal() +theme(legend.position ="none",axis.text.x =element_text(angle =45, hjust =1))# Print the plotprint(violin_plot)# Map of predicted fishing hours only # Prepare the data for the mapmap_data <- combined_data_01deg %>%filter(!has_AIS & has_SAR) %>% dplyr::select(lon_std, lat_std, predicted_fishing_hours)# The map_data now contains back-transformed predictions, so no further transformation is needed#predicted_SAR_only_1RF=map_data#save(predicted_SAR_only_1RF, file="predicted_SAR_only_1RF.Rdata")# Create the world mapworld_map <-map_data("world")# Function to create map for a specific regioncreate_region_map <-function(data, world_map, lon_col, lat_col, lon_range, lat_range, title, subtitle) {ggplot() +geom_map(data = world_map, map = world_map,aes(long, lat, map_id = region),color ="darkgray", fill ="lightgray", size =0.1) +geom_tile(data = data, aes(x = .data[[lon_col]], y = .data[[lat_col]], fill = predicted_fishing_hours)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="Predicted fishing hours (2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000, 100000, 1000000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3, xlim = lon_range, ylim = lat_range) +theme_minimal() +labs(title = title,subtitle = subtitle,x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )}# Global mappredicted_SAR_only_plot <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-180, 180), c(-90, 90), "Predicted Fishing Hours in Areas with Only SAR Detections", "0.1 degree resolution")# Caribbean mapcaribbean_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-100, -50), c(0, 40), "Predicted Fishing Hours in the Caribbean", "0.1 degree resolution")# Northwestern Indian Ocean to Western European waters mapindian_european_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(-20, 80), c(0, 70), "Predicted Fishing Hours from Northern Indian Ocean \nto Eastern Atlantic", "0.1 degree resolution")# Asia mapasia_map <-create_region_map(map_data, world_map, "lon_std", "lat_std", c(60, 180), c(-20, 60), "Predicted Fishing Hours in Asia", "0.1 degree resolution")# Print the maps#print(predicted_SAR_only_plot)print(caribbean_map)print(indian_european_map)print(asia_map)#Map of both original and predicted AIS fishing hours # Visualize the resultspredicted_plot <-ggplot() +geom_map(data = world_map, map = world_map,aes(long, lat, map_id = region),color ="black", fill ="lightgray", size =0.1) +geom_tile(data = combined_data_01deg, aes(x = lon_std, y = lat_std, fill = predicted_fishing_hours)) +scale_fill_viridis(option ="inferno",direction =-1,trans ="log1p",name ="AIS fishing effort (hours; 2017-2020)", breaks =c(0, 1, 10, 100, 1000, 10000, 100000, 1000000),labels = scales::comma,guide =guide_colorbar(barwidth =20, barheight =0.5, title.position ="top", title.hjust =0.5) ) +coord_fixed(1.3) +theme_minimal() +labs(title ="Global fishing hours (0.1 degree resolution)",subtitle ="Based on AIS data and random forest predictions from SAR data",x ="Longitude", y ="Latitude") +theme(legend.position ="bottom",legend.direction ="horizontal",legend.box ="vertical",legend.margin = ggplot2::margin(t =20, r =0, b =0, l =0),legend.title =element_text(margin = ggplot2::margin(b =10)) )print(predicted_plot)# Save the plotggsave(here::here("R", "Outputs", "predicted_plot_SAR_only.png"), plot = predicted_plot,width =12, height =8, dpi =300)```